SaProtHub/Dataset-PTEN_HUMAN

这个数据集包含了人类PTEN蛋白的单点突变及其在深度突变扫描实验中的相应突变效应分数。数据集以氨基酸序列的形式表示蛋白质，并且包含了训练集、验证集和测试集三个部分。标签表示的是每个蛋白质基于深度突变扫描实验的突变适应性分数（蛋白质稳定性），范围从负无穷大到正无穷大，分数越小表示蛋白质越稳定。

This dataset contains single site mutations of the human PTEN protein and their corresponding mutation effect scores from deep mutation scanning experiments. The proteins are represented in the form of amino acid sequences, and the dataset is divided into training, validation, and test sets. The labels represent the mutation fitness score (protein stability) for each protein based on deep mutation scanning experiments, ranging from negative infinity to positive infinity, with smaller scores indicating greater stability.